14 citations · 21 across the 21 of their papers we have counts for
23 papers
PEARL: Adaptive Prefill-Decode Execution with Elasticity for Agentic Reinforcement Learning
Jiaan Zhu, Wei Gao, Youhui Bai +6
Multi-turn rollout dominates the cost of agentic reinforcement learning (RL). Asynchronous execution and elastic GPU resources can accelerate this stage, but adding rollout replica…
SparkDiffusion: Mitigating the High-Sparsity Trap --- A Unified Framework for up to Single-GPU Acceleration of Visual Generation
Yuxi Liu, Haoyu Li, Zekun Zhang +12
Video diffusion transformers are expensive because attention dominates long spatiotemporal token sequences. We identify the \emph{high-sparsity trap}: at extreme attention sparsity…
CrossDistill: Balancing Quality and Diversity via Trajectory-Level Hybrid Few-Step Distillation
Yuxi Liu, Haoyu Li, Yixiang Cai +8
Few-step distillation accelerates diffusion models but must balance diversity and fidelity: trajectory-based distillation preserves mode coverage, while distribution matching sharp…
RoLA: Rotary-Positioned Low-Rank Linear Attention for Efficient Diffusion Transformers
Zekun Zhang, Yixiang Cai, Yuxi Liu +9
Diffusion Transformers (DiTs) achieve strong video generation quality, but their dense spatiotemporal self-attention scales quadratically with sequence length and quickly becomes t…
SCOPE: Subspace Clustering with Online Per-Head Top-K Estimation for Sparse Video Attention
Qi Zhao, Qirui Li, Hanlin Tang +10
Diffusion Transformers (DiTs) incur quadratic self-attention cost over spatiotemporal tokens. Existing training-free sparse attention methods often construct sparse masks from bloc…
Text Template Tokens Are Implicit Semantic Registers in Diffusion Transformers
Maohua Li, Qirui Li, Yanke Zhou +10
Modern text-to-image diffusion transformers (DiTs) generate images through joint attention, in which text and image tokens interact directly within a single sequence. In large-scal…
CKV: Compressed and Composable KV Cache Reuse for Efficient LLM Inference
Chuheng Du, Junyi Chen, Hanlin Tang +7
Long-context inference is central to modern large language model (LLM) applications such as retrieval-augmented generation and multi-document reasoning. To mitigate the growing inf…
Prompt Generation Technical Report
Dan Ou, Gui Ling, Hao Wan +25
Generative retrieval has become an increasingly adopted paradigm for industrial search, recommendation, and advertising systems, delivering significant online gains. Most existing…
Rethinking Cross-Layer Information Routing in Diffusion Transformers
Chao Xu, Maohua Li, Qirui Li +9
Diffusion Transformers (DiTs) have become a de facto backbone of modern visual generation, and nearly every major axis of their design -- tokenization, attention, conditioning, obj…
Full Attention Strikes Back: Transferring Full Attention into Sparse within Hundred Training Steps
Yanke Zhou, Yiduo Li, Hanlin Tang +6
Long-context inference in large language models is bottlenecked by the quadratic cost of full attention. Existing efficient alternatives often rely either on native sparse training…
ROSE: Rollout On Serving GPUs via Cooperative Elasticity for Agentic RL
Wei Gao, Yuheng Zhao, Dilxat Muhtar +13
Agentic reinforcement learning (RL) is reshaping LLM post-training, but end-to-end training time is dominated by compute-intensive, multi-turn rollouts whose resource demand varies…
RT-Lynx: Putting GEMM Sparsity in the Right Place for Diffusion Models
Xing Cong, Hanlin Tang, Kan Liu +3
Diffusion Transformers (DiT) achieve strong performance in image generation but incur substantial inference costs. While prior work has reduced this cost via quantization and disti…
Rethinking Retrieval-Augmentation as Synthesis: A Query-Aware Context Merging Approach
Jiarui Guo, Yuemeng Xu, Zongwei Lv +6
Retrieval-Augmented Generation (RAG) enables Large Language Models (LLMs) to extend their existing knowledge by dynamically incorporating external information. However, practical d…
Shiva-DiT: Residual-Based Differentiable Top- Selection for Efficient Diffusion Transformers
Jiaji Zhang, Hailiang Zhao, Jiaju Wu +3
Diffusion Transformers (DiTs) are costly at high resolution because self-attention scales quadratically with token sequence length. Existing pruning methods do not jointly provide…
Part II: ROLL Flash -- Accelerating RLVR and Agentic Training with Asynchrony
Han Lu, Zichen Liu, Shaopan Xiong +19
Synchronous Reinforcement Learning (RL) post-training has emerged as a crucial step for enhancing Large Language Models (LLMs) with diverse capabilities. However, many systems desi…
RollPacker: Mitigating Long-Tail Rollouts for Fast, Synchronous RL Post-Training
Wei Gao, Yuheng Zhao, Dakai An +11
Reinforcement Learning (RL) is a pivotal post-training technique for enhancing the reasoning capabilities of Large Language Models (LLMs). However, synchronous RL post-training oft…
RecIS: Sparse to Dense, A Unified Training Framework for Recommendation Models
Hua Zong, Qingtao Zeng, Zhengxiong Zhou +31
In this paper, we propose RecIS, a unified Sparse-Dense training framework designed to achieve two primary goals: 1. Unified Framework To create a Unified sparse-dense training fra…
KVTuner: Sensitivity-Aware Layer-Wise Mixed-Precision KV Cache Quantization for Efficient and Nearly Lossless LLM Inference
Xing Li, Zeyu Xing, Yiming Li +6
KV cache quantization can improve Large Language Models (LLMs) inference throughput and latency in long contexts and large batch-size scenarios while preserving LLMs effectiveness.…
DDK: Distilling Domain Knowledge for Efficient Large Language Models
Jiaheng Liu, Chenchen Zhang, Jinyang Guo +13
Despite the advanced intelligence abilities of large language models (LLMs) in various applications, they still face significant computational and storage demands. Knowledge Distil…
D-CPT Law: Domain-specific Continual Pre-Training Scaling Law for Large Language Models
Haoran Que, Jiaheng Liu, Ge Zhang +13
Continual Pre-Training (CPT) on Large Language Models (LLMs) has been widely used to expand the model's fundamental understanding of specific downstream domains (e.g., math and cod…
GBA: A Tuning-free Approach to Switch between Synchronous and Asynchronous Training for Recommendation Model
Wenbo Su, Yuanxing Zhang, Yufeng Cai +9
High-concurrency asynchronous training upon parameter server (PS) architecture and high-performance synchronous training upon all-reduce (AR) architecture are the most commonly dep…
PICASSO: Unleashing the Potential of GPU-centric Training for Wide-and-deep Recommender Systems
Yuanxing Zhang, Langshi Chen, Siran Yang +12
The development of personalized recommendation has significantly improved the accuracy of information matching and the revenue of e-commerce platforms. Recently, it has 2 trends: 1…
M6-T: Exploring Sparse Expert Models and Beyond
An Yang, Junyang Lin, Rui Men +12
Mixture-of-Experts (MoE) models can achieve promising results with outrageous large amount of parameters but constant computation cost, and thus it has become a trend in model scal…